Skip to main content

Need a memorable profile picture? Use this new MIT algorithm

887306 woman women photographer camera taking a picture
Image used with permission by copyright holder
When you say that a photograph is burned into your memory, it turns out you’re not really exaggerating. According to new research from scientists at MIT, certain photographs have a specific sort of staying power that makes them incredibly memorable. Now, the team has created an artificial intelligence system that can actually predict how well your brain will retain a certain image, and which aspects of it will leave the deepest impression. It’s all thanks to deep learning and a pretty advanced algorithm, enabling a computer to tell how memorable a photo in the same way your brain does.

To try the technology out for yourself, simply head over to the LaMem Demo website, where you can upload a photo and determine its memorability score (as assigned by the algorithm, and by extension, your brain). The tool was created after researchers conducted a crowd-sourced experiment involving  5,000 online participants, each of whom were given a set of photos to analyze and then asked to press a key when they came across a familiar image. This data, as well as the particular features of the familiar pictures, was then translated into a memorability score between 0 and 1.

Recommended Videos

“Understanding memorability can help us make systems to capture the most important information, or, conversely, to store information that humans will most likely forget,” said lead study author Aditya Khosla. “It’s like having an instant focus group that tells you how likely it is that someone will remember a visual message.”

Scientists are hopeful that the information gleaned from this research may one day aid in better understanding, and perhaps augmenting, the ability of the human brain to form memories.

“While deep-learning has propelled much progress in object recognition and scene understanding, predicting human memory has often been viewed as a higher-level cognitive process that computer scientists will never be able to tackle,” said research scientist Aude Oliva, who served as a senior investigator for the study. “Well, we can, and we did!”

So if you’re looking for a way to reorganize your Tinder photos, this may just be your saving grace.

Lulu Chang
Former Digital Trends Contributor
Fascinated by the effects of technology on human interaction, Lulu believes that if her parents can use your new app…
A literal minority report: Examining the algorithmic bias of predictive policing
predictive policing bias in the works

Predictive policing was supposed to transform the way policing was carried out, ushering us into a world of smart law enforcement in which bias was removed and police would be able to respond to the data, not to hunches. But a decade after most of us first heard the term “predictive policing” it seems clear that it has not worked. Driven by a public backlash, the technology is experiencing a significant decline in its usage, compared to just a few years ago.

In April this year, Los Angeles -- which, according to the LA Times, “pioneered predicting crime with data” -- cut funding for its predictive policing program, blaming the cost. “That is a hard decision,” Police Chief Michel Moore told the LA Times. “It’s a strategy we used, but the cost projections of hundreds of thousands of dollars to spend on that right now versus finding that money and directing that money to other more central activities is what I have to do.”

Read more
MIT Technology Review predicts the 10 breakthrough technologies of 2020
MIT researchers used a machine-learning algorithm to identify a drug called halicin that kills many strains of bacteria. Halicin (top row) prevented the development of antibiotic resistance in E. coli, while ciprofloxacin (bottom row) did not.

New technologies emerge faster than ever now, but the editors and writers at the MIT Technology Review think they know which ones will be making the biggest impacts this year. The renowned tech magazine published its annual list of the 10 Breakthrough Technologies of 2020 Wednesday morning; editor David Rotman spoke with Digital Trends about why everyone will be talking about tiny A.I., satellite mega-constellations, and anti-aging drugs this year.

“What we do to put the list together is really just ask each of our writers and editors, ‘What are really the most important advances that you've been writing about, thinking about over the last year?’” Rotman told Digital Trends. While it doesn’t have to be the most-covered tech, the breakthroughs that make the list often have multiple companies or organizations working towards making it happen. “We're looking for big trends that are getting a lot of people excited,” he said.

Read more
Researchers use artificial intelligence to develop powerful new antibiotic
MIT researchers used a machine-learning algorithm to identify a drug called halicin that kills many strains of bacteria. Halicin (top row) prevented the development of antibiotic resistance in E. coli, while ciprofloxacin (bottom row) did not.

Researchers at MIT have used artificial intelligence to develop a new antibiotic compound that can kill even some antibiotic-resistant strains of bacteria. They created a computer model of millions of chemical compounds and used a machine-learning algorithm to pick out those which could be effective antibiotics, then selected one particular compound for testing and found it to be effective against E. coli and other bacteria in mouse models.

Most new antibiotics developed today are variations on existing drugs, using the same mechanisms. The new antibiotic uses a different mechanism than these existing drugs, meaning it can treat infections that current drugs cannot.

Read more